{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:21:29Z","timestamp":1768281689227,"version":"3.49.0"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176184"],"award-info":[{"award-number":["62176184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["0006\/2024\/RIA1"],"award-info":[{"award-number":["0006\/2024\/RIA1"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3623492","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:19Z","timestamp":1761153919000},"page":"531-544","source":"Crossref","is-referenced-by-count":0,"title":["Bootstrap Deep Spectral Clustering With Optimal Transport"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9822-9605","authenticated-orcid":false,"given":"Wengang","family":"Guo","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3784-7788","authenticated-orcid":false,"given":"Wei","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"}]},{"given":"Chunchun","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1870-9037","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Taipa, Macau, China"}]},{"given":"Christian","family":"B\u00f6hm","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, University of Vienna, Vienna, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5274-8123","authenticated-orcid":false,"given":"Claudia","family":"Plant","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, University of Vienna, Vienna, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0831-6934","authenticated-orcid":false,"given":"Susanto","family":"Rahardja","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.626"},{"key":"ref5","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.612"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2745702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02166"},{"key":"ref11","first-page":"3861","article-title":"Towards K-means-friendly spaces: Simultaneous deep learning and clustering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref13","first-page":"1668","article-title":"SpectralNet: Spectral clustering using deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shaham","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00419"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/356"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2019.2926450"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533825"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref22","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Cuturi","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289451"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW53433.2021.00090"},{"key":"ref25","first-page":"24","article-title":"Deep subspace clustering networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ji","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025666"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086727"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947199"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3194643"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831693"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00824"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3136098"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135375"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"ref41","first-page":"27734","article-title":"You never cluster alone","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Shen","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347842"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387298"},{"key":"ref44","first-page":"45182","article-title":"Image clustering conditioned on text criteria","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kwon","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.858"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00648"},{"key":"ref47","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/43.159993"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213756"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105822"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2829867"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247748"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3000947"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2889560"},{"key":"ref56","first-page":"1601","article-title":"Self-tuning spectral clustering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zelnik-Manor","year":"2004"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.188"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1262185"},{"key":"ref60","first-page":"655","article-title":"Power iteration clustering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin","year":"2010"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939845"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2358564"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3002587"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966346"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238361"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8683"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/210"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iay008"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3098806"},{"key":"ref70","first-page":"2273","article-title":"A unified framework for discrete spectral clustering","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Yang","year":"2016"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11613"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3398295"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136965"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8916"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref76","first-page":"10992","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Asano","year":"2019"},{"key":"ref77","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref79","first-page":"203","article-title":"A random walks view of spectral segmentation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Meil","year":"2001"},{"key":"ref80","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-0450-1"},{"key":"ref82","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref84","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref85","first-page":"3","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS231N"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00333"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(78)90018-3"},{"key":"ref89","first-page":"1010","article-title":"Locality preserving nonnegative matrix factorization","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Cai","year":"2009"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00909"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369862"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00887"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00948"},{"key":"ref94","first-page":"11177","article-title":"Clustering-friendly representation learning via instance discrimination and feature decorrelation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tao","year":"2021"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3353598"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-024-11597-x"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref98","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref99","first-page":"1769","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2016"},{"key":"ref100","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553511"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024192"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11214477.pdf?arnumber=11214477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:33Z","timestamp":1768255353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11214477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3623492","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}